mlsanityData to 14 Oct 2026

Scalable Federated Learning for Clients with Different Input Image Sizes and Numbers of Output Categories

arXiv 2311.08716 ↗First posted 15 Nov 2023cs.LG cs.CR cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated learning is a privacy-preserving training method which consists of training from a plurality of clients but without sharing their confidential data. However, previous work on federated learning do not explore suitable neural network architectures for clients with different input images sizes and different numbers of output categories. In this paper, we propose an effective federated learning method named ScalableFL, where the depths and widths of the local models for each client are adjusted according to the clients' input image size and the numbers of output categories. In addition, we provide a new bound for the generalization gap of federated learning. In particular, this bound helps to explain the effectiveness of our scalable neural network approach. We demonstrate the effectiveness of ScalableFL in several heterogeneous client settings for both image classification and object detection tasks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 42 references that are in the map. First posted on arXiv 15 Nov 2023.

Builds on

24 of 42 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  7. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  8. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  9. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  10. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  11. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  12. 2017Spectrally-normalized margin bounds for neural networkscited by 686
12 more
  1. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  2. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 564
  3. 2019Federated Learning with Personalization Layerscited by 541
  4. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
  5. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  6. 2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 337
  7. 2018Stronger generalization bounds for deep nets via a compression approachcited by 307
  8. 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
  9. 2021Parameterized Knowledge Transfer for Personalized Federated Learningcited by 109
  10. 2019Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural networkcited by 39
  11. 2021QuPeD: Quantized Personalization via Distillation with Applications to Federated Learningcited by 32
  12. 2020Information-Theoretic Bounds on the Generalization Error and Privacy Leakage in Federated Learningcited by 21

Built on by

Not cited yet.